FLTEval
We show this table for reference; we do not rank on it.
A repository-level Lean 4 proof engineering benchmark that measures whether a model can complete formal proofs and correctly define new mathematical concepts inside realistic FLT project pull requests.
About FLTEval
Year
2026
Tasks
FLT project pull requests
Format
Lean 4 repository task completion
Difficulty
Formal verification / proof engineering
FLTEval is designed to move evaluation beyond isolated competition-math problems. Instead of proving one-off statements, models must operate inside realistic formal repositories and finish pull-request-style Lean 4 work with Lean itself acting as a verifier.
Freshness and provenance
Version
FLTEval 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Questions
What does FLTEval measure?
A repository-level Lean 4 proof engineering benchmark that measures whether a model can complete formal proofs and correctly define new mathematical concepts inside realistic FLT project pull requests.
Which model scores highest on FLTEval?
No sourced model results are published for FLTEval on BenchLM yet.
How many models are evaluated on FLTEval?
0 AI models have published results on FLTEval in the BenchLM catalog.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 7,000+ subscribers.
One email each week. Unsubscribe anytime.